-
-
Notifications
You must be signed in to change notification settings - Fork 4
/
md4c.c
7004 lines (6061 loc) · 191 KB
/
md4c.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* MD4C: Markdown parser for C
* (http://github.com/mity/md4c)
*
* Copyright (c) 2016-2020 Martin Mitas
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include "md4c.h"
#include <limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/*****************************
*** Miscellaneous Stuff ***
*****************************/
#if !defined(__STDC_VERSION__) || __STDC_VERSION__ < 199409L
/* C89/90 or old compilers in general may not understand "inline". */
#if defined __GNUC__
#define inline __inline__
#elif defined _MSC_VER
#define inline __inline
#else
#define inline
#endif
#endif
/* Make the UTF-8 support the default. */
#if !defined MD4C_USE_ASCII && !defined MD4C_USE_UTF8 && !defined MD4C_USE_UTF16
#define MD4C_USE_UTF8
#endif
/* Magic for making wide literals with MD4C_USE_UTF16. */
#ifdef _T
#undef _T
#endif
#if defined MD4C_USE_UTF16
#define _T(x) L##x
#else
#define _T(x) x
#endif
/* Misc. macros. */
#define SIZEOF_ARRAY(a) (sizeof(a) / sizeof(a[0]))
#define STRINGIZE_(x) #x
#define STRINGIZE(x) STRINGIZE_(x)
#ifndef TRUE
#define TRUE 1
#define FALSE 0
#endif
#define MD_LOG(msg) \
do { \
if (ctx->parser.debug_log != NULL) \
ctx->parser.debug_log((msg), ctx->userdata); \
} while (0)
#ifdef DEBUG
#define MD_ASSERT(cond) \
do { \
if (!(cond)) { \
MD_LOG(__FILE__ ":" STRINGIZE(__LINE__) ": " \
"Assertion '" STRINGIZE(cond) "' failed."); \
exit(1); \
} \
} while (0)
#define MD_UNREACHABLE() MD_ASSERT(1 == 0)
#else
#ifdef __GNUC__
#define MD_ASSERT(cond) \
do { \
if (!(cond)) \
__builtin_unreachable(); \
} while (0)
#define MD_UNREACHABLE() \
do { \
__builtin_unreachable(); \
} while (0)
#elif defined _MSC_VER && _MSC_VER > 120
#define MD_ASSERT(cond) \
do { \
__assume(cond); \
} while (0)
#define MD_UNREACHABLE() \
do { \
__assume(0); \
} while (0)
#else
#define MD_ASSERT(cond) \
do { \
} while (0)
#define MD_UNREACHABLE() \
do { \
} while (0)
#endif
#endif
/* For falling through case labels in switch statements. */
#if defined __clang__ && __clang_major__ >= 12
#define MD_FALLTHROUGH() __attribute__((fallthrough))
#elif defined __GNUC__ && __GNUC__ >= 7
#define MD_FALLTHROUGH() __attribute__((fallthrough))
#else
#define MD_FALLTHROUGH() ((void)0)
#endif
/* Suppress "unused parameter" warnings. */
#define MD_UNUSED(x) ((void)x)
/************************
*** Internal Types ***
************************/
/* These are omnipresent so lets save some typing. */
#define CHAR MD_CHAR
#define SZ MD_SIZE
#define OFF MD_OFFSET
typedef struct MD_MARK_tag MD_MARK;
typedef struct MD_BLOCK_tag MD_BLOCK;
typedef struct MD_CONTAINER_tag MD_CONTAINER;
typedef struct MD_REF_DEF_tag MD_REF_DEF;
/* During analyzes of inline marks, we need to manage some "mark chains",
* of (yet unresolved) openers. This structure holds start/end of the chain.
* The chain internals are then realized through MD_MARK::prev and ::next.
*/
typedef struct MD_MARKCHAIN_tag MD_MARKCHAIN;
struct MD_MARKCHAIN_tag {
int head; /* Index of first mark in the chain, or -1 if empty. */
int tail; /* Index of last mark in the chain, or -1 if empty. */
};
/* Context propagated through all the parsing. */
typedef struct MD_CTX_tag MD_CTX;
struct MD_CTX_tag {
/* Immutable stuff (parameters of md_parse()). */
const CHAR *text;
SZ size;
MD_PARSER parser;
void *userdata;
/* When this is true, it allows some optimizations. */
int doc_ends_with_newline;
/* Helper temporary growing buffer. */
CHAR *buffer;
unsigned alloc_buffer;
/* Reference definitions. */
MD_REF_DEF *ref_defs;
int n_ref_defs;
int alloc_ref_defs;
void **ref_def_hashtable;
int ref_def_hashtable_size;
/* Stack of inline/span markers.
* This is only used for parsing a single block contents but by storing it
* here we may reuse the stack for subsequent blocks; i.e. we have fewer
* (re)allocations. */
MD_MARK *marks;
int n_marks;
int alloc_marks;
#if defined MD4C_USE_UTF16
char mark_char_map[128];
#else
char mark_char_map[256];
#endif
/* For resolving of inline spans. */
MD_MARKCHAIN mark_chains[13];
#define PTR_CHAIN (ctx->mark_chains[0])
#define TABLECELLBOUNDARIES (ctx->mark_chains[1])
#define ASTERISK_OPENERS_extraword_mod3_0 (ctx->mark_chains[2])
#define ASTERISK_OPENERS_extraword_mod3_1 (ctx->mark_chains[3])
#define ASTERISK_OPENERS_extraword_mod3_2 (ctx->mark_chains[4])
#define ASTERISK_OPENERS_intraword_mod3_0 (ctx->mark_chains[5])
#define ASTERISK_OPENERS_intraword_mod3_1 (ctx->mark_chains[6])
#define ASTERISK_OPENERS_intraword_mod3_2 (ctx->mark_chains[7])
#define UNDERSCORE_OPENERS (ctx->mark_chains[8])
#define TILDE_OPENERS_1 (ctx->mark_chains[9])
#define TILDE_OPENERS_2 (ctx->mark_chains[10])
#define BRACKET_OPENERS (ctx->mark_chains[11])
#define DOLLAR_OPENERS (ctx->mark_chains[12])
#define OPENERS_CHAIN_FIRST 1
#define OPENERS_CHAIN_LAST 12
int n_table_cell_boundaries;
/* For resolving links. */
int unresolved_link_head;
int unresolved_link_tail;
/* For resolving raw HTML. */
OFF html_comment_horizon;
OFF html_proc_instr_horizon;
OFF html_decl_horizon;
OFF html_cdata_horizon;
/* For block analysis.
* Notes:
* -- It holds MD_BLOCK as well as MD_LINE structures. After each
* MD_BLOCK, its (multiple) MD_LINE(s) follow.
* -- For MD_BLOCK_HTML and MD_BLOCK_CODE, MD_VERBATIMLINE(s) are used
* instead of MD_LINE(s).
*/
void *block_bytes;
MD_BLOCK *current_block;
int n_block_bytes;
int alloc_block_bytes;
/* For container block analysis. */
MD_CONTAINER *containers;
int n_containers;
int alloc_containers;
/* Minimal indentation to call the block "indented code block". */
unsigned code_indent_offset;
/* Contextual info for line analysis. */
SZ code_fence_length; /* For checking closing fence length. */
int html_block_type; /* For checking closing raw HTML condition. */
int last_line_has_list_loosening_effect;
int last_list_item_starts_with_two_blank_lines;
};
enum MD_LINETYPE_tag {
MD_LINE_BLANK,
MD_LINE_HR,
MD_LINE_ATXHEADER,
MD_LINE_SETEXTHEADER,
MD_LINE_SETEXTUNDERLINE,
MD_LINE_INDENTEDCODE,
MD_LINE_FENCEDCODE,
MD_LINE_HTML,
MD_LINE_TEXT,
MD_LINE_TABLE,
MD_LINE_TABLEUNDERLINE
};
typedef enum MD_LINETYPE_tag MD_LINETYPE;
typedef struct MD_LINE_ANALYSIS_tag MD_LINE_ANALYSIS;
struct MD_LINE_ANALYSIS_tag {
MD_LINETYPE type : 16;
unsigned data : 16;
OFF beg;
OFF end;
unsigned indent; /* Indentation level. */
};
typedef struct MD_LINE_tag MD_LINE;
struct MD_LINE_tag {
OFF beg;
OFF end;
};
typedef struct MD_VERBATIMLINE_tag MD_VERBATIMLINE;
struct MD_VERBATIMLINE_tag {
OFF beg;
OFF end;
OFF indent;
};
/*****************
*** Helpers ***
*****************/
/* Character accessors. */
#define CH(off) (ctx->text[(off)])
#define STR(off) (ctx->text + (off))
/* Character classification.
* Note we assume ASCII compatibility of code points < 128 here. */
#define ISIN_(ch, ch_min, ch_max) \
((ch_min) <= (unsigned)(ch) && (unsigned)(ch) <= (ch_max))
#define ISANYOF_(ch, palette) \
((ch) != _T('\0') && md_strchr((palette), (ch)) != NULL)
#define ISANYOF2_(ch, ch1, ch2) ((ch) == (ch1) || (ch) == (ch2))
#define ISANYOF3_(ch, ch1, ch2, ch3) \
((ch) == (ch1) || (ch) == (ch2) || (ch) == (ch3))
#define ISASCII_(ch) ((unsigned)(ch) <= 127)
#define ISBLANK_(ch) (ISANYOF2_((ch), _T(' '), _T('\t')))
#define ISNEWLINE_(ch) (ISANYOF2_((ch), _T('\r'), _T('\n')))
#define ISWHITESPACE_(ch) (ISBLANK_(ch) || ISANYOF2_((ch), _T('\v'), _T('\f')))
#define ISCNTRL_(ch) ((unsigned)(ch) <= 31 || (unsigned)(ch) == 127)
#define ISPUNCT_(ch) \
(ISIN_(ch, 33, 47) || ISIN_(ch, 58, 64) || ISIN_(ch, 91, 96) || \
ISIN_(ch, 123, 126))
#define ISUPPER_(ch) (ISIN_(ch, _T('A'), _T('Z')))
#define ISLOWER_(ch) (ISIN_(ch, _T('a'), _T('z')))
#define ISALPHA_(ch) (ISUPPER_(ch) || ISLOWER_(ch))
#define ISDIGIT_(ch) (ISIN_(ch, _T('0'), _T('9')))
#define ISXDIGIT_(ch) \
(ISDIGIT_(ch) || ISIN_(ch, _T('A'), _T('F')) || \
ISIN_(ch, _T('a'), _T('f')))
#define ISALNUM_(ch) (ISALPHA_(ch) || ISDIGIT_(ch))
#define ISANYOF(off, palette) ISANYOF_(CH(off), (palette))
#define ISANYOF2(off, ch1, ch2) ISANYOF2_(CH(off), (ch1), (ch2))
#define ISANYOF3(off, ch1, ch2, ch3) ISANYOF3_(CH(off), (ch1), (ch2), (ch3))
#define ISASCII(off) ISASCII_(CH(off))
#define ISBLANK(off) ISBLANK_(CH(off))
#define ISNEWLINE(off) ISNEWLINE_(CH(off))
#define ISWHITESPACE(off) ISWHITESPACE_(CH(off))
#define ISCNTRL(off) ISCNTRL_(CH(off))
#define ISPUNCT(off) ISPUNCT_(CH(off))
#define ISUPPER(off) ISUPPER_(CH(off))
#define ISLOWER(off) ISLOWER_(CH(off))
#define ISALPHA(off) ISALPHA_(CH(off))
#define ISDIGIT(off) ISDIGIT_(CH(off))
#define ISXDIGIT(off) ISXDIGIT_(CH(off))
#define ISALNUM(off) ISALNUM_(CH(off))
#if defined MD4C_USE_UTF16
#define md_strchr wcschr
#else
#define md_strchr strchr
#endif
/* Case insensitive check of string equality. */
static inline int md_ascii_case_eq(const CHAR *s1, const CHAR *s2, SZ n)
{
OFF i;
for (i = 0; i < n; i++) {
CHAR ch1 = s1[i];
CHAR ch2 = s2[i];
if (ISLOWER_(ch1))
ch1 += ('A' - 'a');
if (ISLOWER_(ch2))
ch2 += ('A' - 'a');
if (ch1 != ch2)
return FALSE;
}
return TRUE;
}
static inline int md_ascii_eq(const CHAR *s1, const CHAR *s2, SZ n)
{
return memcmp(s1, s2, n * sizeof(CHAR)) == 0;
}
static int md_text_with_null_replacement(MD_CTX *ctx, MD_TEXTTYPE type,
const CHAR *str, SZ size)
{
OFF off = 0;
int ret = 0;
while (1) {
while (off < size && str[off] != _T('\0'))
off++;
if (off > 0) {
ret = ctx->parser.text(type, str, off, ctx->userdata);
if (ret != 0)
return ret;
str += off;
size -= off;
off = 0;
}
if (off >= size)
return 0;
ret = ctx->parser.text(MD_TEXT_NULLCHAR, _T(""), 1,
ctx->userdata);
if (ret != 0)
return ret;
off++;
}
}
#define MD_CHECK(func) \
do { \
ret = (func); \
if (ret < 0) \
goto abort; \
} while (0)
#define MD_TEMP_BUFFER(sz) \
do { \
if (sz > ctx->alloc_buffer) { \
CHAR *new_buffer; \
SZ new_size = ((sz) + (sz) / 2 + 128) & ~127; \
\
new_buffer = realloc(ctx->buffer, new_size); \
if (new_buffer == NULL) { \
MD_LOG("realloc() failed."); \
ret = -1; \
goto abort; \
} \
\
ctx->buffer = new_buffer; \
ctx->alloc_buffer = new_size; \
} \
} while (0)
#define MD_ENTER_BLOCK(type, arg) \
do { \
ret = ctx->parser.enter_block((type), (arg), ctx->userdata); \
if (ret != 0) { \
MD_LOG("Aborted from enter_block() callback."); \
goto abort; \
} \
} while (0)
#define MD_LEAVE_BLOCK(type, arg) \
do { \
ret = ctx->parser.leave_block((type), (arg), ctx->userdata); \
if (ret != 0) { \
MD_LOG("Aborted from leave_block() callback."); \
goto abort; \
} \
} while (0)
#define MD_ENTER_SPAN(type, arg) \
do { \
ret = ctx->parser.enter_span((type), (arg), ctx->userdata); \
if (ret != 0) { \
MD_LOG("Aborted from enter_span() callback."); \
goto abort; \
} \
} while (0)
#define MD_LEAVE_SPAN(type, arg) \
do { \
ret = ctx->parser.leave_span((type), (arg), ctx->userdata); \
if (ret != 0) { \
MD_LOG("Aborted from leave_span() callback."); \
goto abort; \
} \
} while (0)
#define MD_TEXT(type, str, size) \
do { \
if (size > 0) { \
ret = ctx->parser.text((type), (str), (size), \
ctx->userdata); \
if (ret != 0) { \
MD_LOG("Aborted from text() callback."); \
goto abort; \
} \
} \
} while (0)
#define MD_TEXT_INSECURE(type, str, size) \
do { \
if (size > 0) { \
ret = md_text_with_null_replacement(ctx, type, str, \
size); \
if (ret != 0) { \
MD_LOG("Aborted from text() callback."); \
goto abort; \
} \
} \
} while (0)
/* If the offset falls into a gap between line, we return the following
* line. */
static const MD_LINE *md_lookup_line(OFF off, const MD_LINE *lines, int n_lines)
{
int lo, hi;
int pivot;
const MD_LINE *line;
lo = 0;
hi = n_lines - 1;
while (lo <= hi) {
pivot = (lo + hi) / 2;
line = &lines[pivot];
if (off < line->beg) {
hi = pivot - 1;
if (hi < 0 || lines[hi].end <= off)
return line;
} else if (off > line->end) {
lo = pivot + 1;
} else {
return line;
}
}
return NULL;
}
/*************************
*** Unicode Support ***
*************************/
typedef struct MD_UNICODE_FOLD_INFO_tag MD_UNICODE_FOLD_INFO;
struct MD_UNICODE_FOLD_INFO_tag {
unsigned codepoints[3];
unsigned n_codepoints;
};
#if defined MD4C_USE_UTF16 || defined MD4C_USE_UTF8
/* Binary search over sorted "map" of codepoints. Consecutive sequences
* of codepoints may be encoded in the map by just using the
* (MIN_CODEPOINT | 0x40000000) and (MAX_CODEPOINT | 0x80000000).
*
* Returns index of the found record in the map (in the case of ranges,
* the minimal value is used); or -1 on failure. */
static int md_unicode_bsearch__(unsigned codepoint, const unsigned *map,
size_t map_size)
{
int beg, end;
int pivot_beg, pivot_end;
beg = 0;
end = (int)map_size - 1;
while (beg <= end) {
/* Pivot may be a range, not just a single value. */
pivot_beg = pivot_end = (beg + end) / 2;
if (map[pivot_end] & 0x40000000)
pivot_end++;
if (map[pivot_beg] & 0x80000000)
pivot_beg--;
if (codepoint < (map[pivot_beg] & 0x00ffffff))
end = pivot_beg - 1;
else if (codepoint > (map[pivot_end] & 0x00ffffff))
beg = pivot_end + 1;
else
return pivot_beg;
}
return -1;
}
static int md_is_unicode_whitespace__(unsigned codepoint)
{
#define R(cp_min, cp_max) ((cp_min) | 0x40000000), ((cp_max) | 0x80000000)
#define S(cp) (cp)
/* Unicode "Zs" category.
* (generated by scripts/build_whitespace_map.py) */
static const unsigned WHITESPACE_MAP[] = {S(0x0020), S(0x00a0),
S(0x1680), R(0x2000, 0x200a),
S(0x202f), S(0x205f),
S(0x3000)};
#undef R
#undef S
/* The ASCII ones are the most frequently used ones, also CommonMark
* specification requests few more in this range. */
if (codepoint <= 0x7f)
return ISWHITESPACE_(codepoint);
return (md_unicode_bsearch__(codepoint, WHITESPACE_MAP,
SIZEOF_ARRAY(WHITESPACE_MAP)) >= 0);
}
static int md_is_unicode_punct__(unsigned codepoint)
{
#define R(cp_min, cp_max) ((cp_min) | 0x40000000), ((cp_max) | 0x80000000)
#define S(cp) (cp)
/* Unicode "Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps" categories.
* (generated by scripts/build_punct_map.py) */
static const unsigned PUNCT_MAP[] = {
R(0x0021, 0x0023), R(0x0025, 0x002a), R(0x002c, 0x002f),
R(0x003a, 0x003b), R(0x003f, 0x0040), R(0x005b, 0x005d),
S(0x005f), S(0x007b), S(0x007d),
S(0x00a1), S(0x00a7), S(0x00ab),
R(0x00b6, 0x00b7), S(0x00bb), S(0x00bf),
S(0x037e), S(0x0387), R(0x055a, 0x055f),
R(0x0589, 0x058a), S(0x05be), S(0x05c0),
S(0x05c3), S(0x05c6), R(0x05f3, 0x05f4),
R(0x0609, 0x060a), R(0x060c, 0x060d), S(0x061b),
R(0x061e, 0x061f), R(0x066a, 0x066d), S(0x06d4),
R(0x0700, 0x070d), R(0x07f7, 0x07f9), R(0x0830, 0x083e),
S(0x085e), R(0x0964, 0x0965), S(0x0970),
S(0x09fd), S(0x0a76), S(0x0af0),
S(0x0c77), S(0x0c84), S(0x0df4),
S(0x0e4f), R(0x0e5a, 0x0e5b), R(0x0f04, 0x0f12),
S(0x0f14), R(0x0f3a, 0x0f3d), S(0x0f85),
R(0x0fd0, 0x0fd4), R(0x0fd9, 0x0fda), R(0x104a, 0x104f),
S(0x10fb), R(0x1360, 0x1368), S(0x1400),
S(0x166e), R(0x169b, 0x169c), R(0x16eb, 0x16ed),
R(0x1735, 0x1736), R(0x17d4, 0x17d6), R(0x17d8, 0x17da),
R(0x1800, 0x180a), R(0x1944, 0x1945), R(0x1a1e, 0x1a1f),
R(0x1aa0, 0x1aa6), R(0x1aa8, 0x1aad), R(0x1b5a, 0x1b60),
R(0x1bfc, 0x1bff), R(0x1c3b, 0x1c3f), R(0x1c7e, 0x1c7f),
R(0x1cc0, 0x1cc7), S(0x1cd3), R(0x2010, 0x2027),
R(0x2030, 0x2043), R(0x2045, 0x2051), R(0x2053, 0x205e),
R(0x207d, 0x207e), R(0x208d, 0x208e), R(0x2308, 0x230b),
R(0x2329, 0x232a), R(0x2768, 0x2775), R(0x27c5, 0x27c6),
R(0x27e6, 0x27ef), R(0x2983, 0x2998), R(0x29d8, 0x29db),
R(0x29fc, 0x29fd), R(0x2cf9, 0x2cfc), R(0x2cfe, 0x2cff),
S(0x2d70), R(0x2e00, 0x2e2e), R(0x2e30, 0x2e4f),
S(0x2e52), R(0x3001, 0x3003), R(0x3008, 0x3011),
R(0x3014, 0x301f), S(0x3030), S(0x303d),
S(0x30a0), S(0x30fb), R(0xa4fe, 0xa4ff),
R(0xa60d, 0xa60f), S(0xa673), S(0xa67e),
R(0xa6f2, 0xa6f7), R(0xa874, 0xa877), R(0xa8ce, 0xa8cf),
R(0xa8f8, 0xa8fa), S(0xa8fc), R(0xa92e, 0xa92f),
S(0xa95f), R(0xa9c1, 0xa9cd), R(0xa9de, 0xa9df),
R(0xaa5c, 0xaa5f), R(0xaade, 0xaadf), R(0xaaf0, 0xaaf1),
S(0xabeb), R(0xfd3e, 0xfd3f), R(0xfe10, 0xfe19),
R(0xfe30, 0xfe52), R(0xfe54, 0xfe61), S(0xfe63),
S(0xfe68), R(0xfe6a, 0xfe6b), R(0xff01, 0xff03),
R(0xff05, 0xff0a), R(0xff0c, 0xff0f), R(0xff1a, 0xff1b),
R(0xff1f, 0xff20), R(0xff3b, 0xff3d), S(0xff3f),
S(0xff5b), S(0xff5d), R(0xff5f, 0xff65),
R(0x10100, 0x10102), S(0x1039f), S(0x103d0),
S(0x1056f), S(0x10857), S(0x1091f),
S(0x1093f), R(0x10a50, 0x10a58), S(0x10a7f),
R(0x10af0, 0x10af6), R(0x10b39, 0x10b3f), R(0x10b99, 0x10b9c),
S(0x10ead), R(0x10f55, 0x10f59), R(0x11047, 0x1104d),
R(0x110bb, 0x110bc), R(0x110be, 0x110c1), R(0x11140, 0x11143),
R(0x11174, 0x11175), R(0x111c5, 0x111c8), S(0x111cd),
S(0x111db), R(0x111dd, 0x111df), R(0x11238, 0x1123d),
S(0x112a9), R(0x1144b, 0x1144f), R(0x1145a, 0x1145b),
S(0x1145d), S(0x114c6), R(0x115c1, 0x115d7),
R(0x11641, 0x11643), R(0x11660, 0x1166c), R(0x1173c, 0x1173e),
S(0x1183b), R(0x11944, 0x11946), S(0x119e2),
R(0x11a3f, 0x11a46), R(0x11a9a, 0x11a9c), R(0x11a9e, 0x11aa2),
R(0x11c41, 0x11c45), R(0x11c70, 0x11c71), R(0x11ef7, 0x11ef8),
S(0x11fff), R(0x12470, 0x12474), R(0x16a6e, 0x16a6f),
S(0x16af5), R(0x16b37, 0x16b3b), S(0x16b44),
R(0x16e97, 0x16e9a), S(0x16fe2), S(0x1bc9f),
R(0x1da87, 0x1da8b), R(0x1e95e, 0x1e95f)};
#undef R
#undef S
/* The ASCII ones are the most frequently used ones, also CommonMark
* specification requests few more in this range. */
if (codepoint <= 0x7f)
return ISPUNCT_(codepoint);
return (md_unicode_bsearch__(codepoint, PUNCT_MAP,
SIZEOF_ARRAY(PUNCT_MAP)) >= 0);
}
static void md_get_unicode_fold_info(unsigned codepoint,
MD_UNICODE_FOLD_INFO *info)
{
#define R(cp_min, cp_max) ((cp_min) | 0x40000000), ((cp_max) | 0x80000000)
#define S(cp) (cp)
/* Unicode "Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps" categories.
* (generated by scripts/build_folding_map.py) */
static const unsigned FOLD_MAP_1[] = {
R(0x0041, 0x005a), S(0x00b5), R(0x00c0, 0x00d6),
R(0x00d8, 0x00de), R(0x0100, 0x012e), R(0x0132, 0x0136),
R(0x0139, 0x0147), R(0x014a, 0x0176), S(0x0178),
R(0x0179, 0x017d), S(0x017f), S(0x0181),
S(0x0182), S(0x0184), S(0x0186),
S(0x0187), S(0x0189), S(0x018a),
S(0x018b), S(0x018e), S(0x018f),
S(0x0190), S(0x0191), S(0x0193),
S(0x0194), S(0x0196), S(0x0197),
S(0x0198), S(0x019c), S(0x019d),
S(0x019f), R(0x01a0, 0x01a4), S(0x01a6),
S(0x01a7), S(0x01a9), S(0x01ac),
S(0x01ae), S(0x01af), S(0x01b1),
S(0x01b2), S(0x01b3), S(0x01b5),
S(0x01b7), S(0x01b8), S(0x01bc),
S(0x01c4), S(0x01c5), S(0x01c7),
S(0x01c8), S(0x01ca), R(0x01cb, 0x01db),
R(0x01de, 0x01ee), S(0x01f1), S(0x01f2),
S(0x01f4), S(0x01f6), S(0x01f7),
R(0x01f8, 0x021e), S(0x0220), R(0x0222, 0x0232),
S(0x023a), S(0x023b), S(0x023d),
S(0x023e), S(0x0241), S(0x0243),
S(0x0244), S(0x0245), R(0x0246, 0x024e),
S(0x0345), S(0x0370), S(0x0372),
S(0x0376), S(0x037f), S(0x0386),
R(0x0388, 0x038a), S(0x038c), S(0x038e),
S(0x038f), R(0x0391, 0x03a1), R(0x03a3, 0x03ab),
S(0x03c2), S(0x03cf), S(0x03d0),
S(0x03d1), S(0x03d5), S(0x03d6),
R(0x03d8, 0x03ee), S(0x03f0), S(0x03f1),
S(0x03f4), S(0x03f5), S(0x03f7),
S(0x03f9), S(0x03fa), R(0x03fd, 0x03ff),
R(0x0400, 0x040f), R(0x0410, 0x042f), R(0x0460, 0x0480),
R(0x048a, 0x04be), S(0x04c0), R(0x04c1, 0x04cd),
R(0x04d0, 0x052e), R(0x0531, 0x0556), R(0x10a0, 0x10c5),
S(0x10c7), S(0x10cd), R(0x13f8, 0x13fd),
S(0x1c80), S(0x1c81), S(0x1c82),
S(0x1c83), S(0x1c84), S(0x1c85),
S(0x1c86), S(0x1c87), S(0x1c88),
R(0x1c90, 0x1cba), R(0x1cbd, 0x1cbf), R(0x1e00, 0x1e94),
S(0x1e9b), R(0x1ea0, 0x1efe), R(0x1f08, 0x1f0f),
R(0x1f18, 0x1f1d), R(0x1f28, 0x1f2f), R(0x1f38, 0x1f3f),
R(0x1f48, 0x1f4d), S(0x1f59), S(0x1f5b),
S(0x1f5d), S(0x1f5f), R(0x1f68, 0x1f6f),
S(0x1fb8), S(0x1fb9), S(0x1fba),
S(0x1fbb), S(0x1fbe), R(0x1fc8, 0x1fcb),
S(0x1fd8), S(0x1fd9), S(0x1fda),
S(0x1fdb), S(0x1fe8), S(0x1fe9),
S(0x1fea), S(0x1feb), S(0x1fec),
S(0x1ff8), S(0x1ff9), S(0x1ffa),
S(0x1ffb), S(0x2126), S(0x212a),
S(0x212b), S(0x2132), R(0x2160, 0x216f),
S(0x2183), R(0x24b6, 0x24cf), R(0x2c00, 0x2c2e),
S(0x2c60), S(0x2c62), S(0x2c63),
S(0x2c64), R(0x2c67, 0x2c6b), S(0x2c6d),
S(0x2c6e), S(0x2c6f), S(0x2c70),
S(0x2c72), S(0x2c75), S(0x2c7e),
S(0x2c7f), R(0x2c80, 0x2ce2), S(0x2ceb),
S(0x2ced), S(0x2cf2), R(0xa640, 0xa66c),
R(0xa680, 0xa69a), R(0xa722, 0xa72e), R(0xa732, 0xa76e),
S(0xa779), S(0xa77b), S(0xa77d),
R(0xa77e, 0xa786), S(0xa78b), S(0xa78d),
S(0xa790), S(0xa792), R(0xa796, 0xa7a8),
S(0xa7aa), S(0xa7ab), S(0xa7ac),
S(0xa7ad), S(0xa7ae), S(0xa7b0),
S(0xa7b1), S(0xa7b2), S(0xa7b3),
R(0xa7b4, 0xa7be), S(0xa7c2), S(0xa7c4),
S(0xa7c5), S(0xa7c6), S(0xa7c7),
S(0xa7c9), S(0xa7f5), R(0xab70, 0xabbf),
R(0xff21, 0xff3a), R(0x10400, 0x10427), R(0x104b0, 0x104d3),
R(0x10c80, 0x10cb2), R(0x118a0, 0x118bf), R(0x16e40, 0x16e5f),
R(0x1e900, 0x1e921)};
static const unsigned FOLD_MAP_1_DATA[] = {
0x0061, 0x007a, 0x03bc, 0x00e0, 0x00f6, 0x00f8, 0x00fe,
0x0101, 0x012f, 0x0133, 0x0137, 0x013a, 0x0148, 0x014b,
0x0177, 0x00ff, 0x017a, 0x017e, 0x0073, 0x0253, 0x0183,
0x0185, 0x0254, 0x0188, 0x0256, 0x0257, 0x018c, 0x01dd,
0x0259, 0x025b, 0x0192, 0x0260, 0x0263, 0x0269, 0x0268,
0x0199, 0x026f, 0x0272, 0x0275, 0x01a1, 0x01a5, 0x0280,
0x01a8, 0x0283, 0x01ad, 0x0288, 0x01b0, 0x028a, 0x028b,
0x01b4, 0x01b6, 0x0292, 0x01b9, 0x01bd, 0x01c6, 0x01c6,
0x01c9, 0x01c9, 0x01cc, 0x01cc, 0x01dc, 0x01df, 0x01ef,
0x01f3, 0x01f3, 0x01f5, 0x0195, 0x01bf, 0x01f9, 0x021f,
0x019e, 0x0223, 0x0233, 0x2c65, 0x023c, 0x019a, 0x2c66,
0x0242, 0x0180, 0x0289, 0x028c, 0x0247, 0x024f, 0x03b9,
0x0371, 0x0373, 0x0377, 0x03f3, 0x03ac, 0x03ad, 0x03af,
0x03cc, 0x03cd, 0x03ce, 0x03b1, 0x03c1, 0x03c3, 0x03cb,
0x03c3, 0x03d7, 0x03b2, 0x03b8, 0x03c6, 0x03c0, 0x03d9,
0x03ef, 0x03ba, 0x03c1, 0x03b8, 0x03b5, 0x03f8, 0x03f2,
0x03fb, 0x037b, 0x037d, 0x0450, 0x045f, 0x0430, 0x044f,
0x0461, 0x0481, 0x048b, 0x04bf, 0x04cf, 0x04c2, 0x04ce,
0x04d1, 0x052f, 0x0561, 0x0586, 0x2d00, 0x2d25, 0x2d27,
0x2d2d, 0x13f0, 0x13f5, 0x0432, 0x0434, 0x043e, 0x0441,
0x0442, 0x0442, 0x044a, 0x0463, 0xa64b, 0x10d0, 0x10fa,
0x10fd, 0x10ff, 0x1e01, 0x1e95, 0x1e61, 0x1ea1, 0x1eff,
0x1f00, 0x1f07, 0x1f10, 0x1f15, 0x1f20, 0x1f27, 0x1f30,
0x1f37, 0x1f40, 0x1f45, 0x1f51, 0x1f53, 0x1f55, 0x1f57,
0x1f60, 0x1f67, 0x1fb0, 0x1fb1, 0x1f70, 0x1f71, 0x03b9,
0x1f72, 0x1f75, 0x1fd0, 0x1fd1, 0x1f76, 0x1f77, 0x1fe0,
0x1fe1, 0x1f7a, 0x1f7b, 0x1fe5, 0x1f78, 0x1f79, 0x1f7c,
0x1f7d, 0x03c9, 0x006b, 0x00e5, 0x214e, 0x2170, 0x217f,
0x2184, 0x24d0, 0x24e9, 0x2c30, 0x2c5e, 0x2c61, 0x026b,
0x1d7d, 0x027d, 0x2c68, 0x2c6c, 0x0251, 0x0271, 0x0250,
0x0252, 0x2c73, 0x2c76, 0x023f, 0x0240, 0x2c81, 0x2ce3,
0x2cec, 0x2cee, 0x2cf3, 0xa641, 0xa66d, 0xa681, 0xa69b,
0xa723, 0xa72f, 0xa733, 0xa76f, 0xa77a, 0xa77c, 0x1d79,
0xa77f, 0xa787, 0xa78c, 0x0265, 0xa791, 0xa793, 0xa797,
0xa7a9, 0x0266, 0x025c, 0x0261, 0x026c, 0x026a, 0x029e,
0x0287, 0x029d, 0xab53, 0xa7b5, 0xa7bf, 0xa7c3, 0xa794,
0x0282, 0x1d8e, 0xa7c8, 0xa7ca, 0xa7f6, 0x13a0, 0x13ef,
0xff41, 0xff5a, 0x10428, 0x1044f, 0x104d8, 0x104fb, 0x10cc0,
0x10cf2, 0x118c0, 0x118df, 0x16e60, 0x16e7f, 0x1e922, 0x1e943};
static const unsigned FOLD_MAP_2[] = {
S(0x00df), S(0x0130), S(0x0149),
S(0x01f0), S(0x0587), S(0x1e96),
S(0x1e97), S(0x1e98), S(0x1e99),
S(0x1e9a), S(0x1e9e), S(0x1f50),
R(0x1f80, 0x1f87), R(0x1f88, 0x1f8f), R(0x1f90, 0x1f97),
R(0x1f98, 0x1f9f), R(0x1fa0, 0x1fa7), R(0x1fa8, 0x1faf),
S(0x1fb2), S(0x1fb3), S(0x1fb4),
S(0x1fb6), S(0x1fbc), S(0x1fc2),
S(0x1fc3), S(0x1fc4), S(0x1fc6),
S(0x1fcc), S(0x1fd6), S(0x1fe4),
S(0x1fe6), S(0x1ff2), S(0x1ff3),
S(0x1ff4), S(0x1ff6), S(0x1ffc),
S(0xfb00), S(0xfb01), S(0xfb02),
S(0xfb05), S(0xfb06), S(0xfb13),
S(0xfb14), S(0xfb15), S(0xfb16),
S(0xfb17)};
static const unsigned FOLD_MAP_2_DATA[] = {
0x0073, 0x0073, 0x0069, 0x0307, 0x02bc, 0x006e, 0x006a, 0x030c,
0x0565, 0x0582, 0x0068, 0x0331, 0x0074, 0x0308, 0x0077, 0x030a,
0x0079, 0x030a, 0x0061, 0x02be, 0x0073, 0x0073, 0x03c5, 0x0313,
0x1f00, 0x03b9, 0x1f07, 0x03b9, 0x1f00, 0x03b9, 0x1f07, 0x03b9,
0x1f20, 0x03b9, 0x1f27, 0x03b9, 0x1f20, 0x03b9, 0x1f27, 0x03b9,
0x1f60, 0x03b9, 0x1f67, 0x03b9, 0x1f60, 0x03b9, 0x1f67, 0x03b9,
0x1f70, 0x03b9, 0x03b1, 0x03b9, 0x03ac, 0x03b9, 0x03b1, 0x0342,
0x03b1, 0x03b9, 0x1f74, 0x03b9, 0x03b7, 0x03b9, 0x03ae, 0x03b9,
0x03b7, 0x0342, 0x03b7, 0x03b9, 0x03b9, 0x0342, 0x03c1, 0x0313,
0x03c5, 0x0342, 0x1f7c, 0x03b9, 0x03c9, 0x03b9, 0x03ce, 0x03b9,
0x03c9, 0x0342, 0x03c9, 0x03b9, 0x0066, 0x0066, 0x0066, 0x0069,
0x0066, 0x006c, 0x0073, 0x0074, 0x0073, 0x0074, 0x0574, 0x0576,
0x0574, 0x0565, 0x0574, 0x056b, 0x057e, 0x0576, 0x0574, 0x056d};
static const unsigned FOLD_MAP_3[] = {S(0x0390), S(0x03b0), S(0x1f52),
S(0x1f54), S(0x1f56), S(0x1fb7),
S(0x1fc7), S(0x1fd2), S(0x1fd3),
S(0x1fd7), S(0x1fe2), S(0x1fe3),
S(0x1fe7), S(0x1ff7), S(0xfb03),
S(0xfb04)};
static const unsigned FOLD_MAP_3_DATA[] = {
0x03b9, 0x0308, 0x0301, 0x03c5, 0x0308, 0x0301, 0x03c5, 0x0313,
0x0300, 0x03c5, 0x0313, 0x0301, 0x03c5, 0x0313, 0x0342, 0x03b1,
0x0342, 0x03b9, 0x03b7, 0x0342, 0x03b9, 0x03b9, 0x0308, 0x0300,
0x03b9, 0x0308, 0x0301, 0x03b9, 0x0308, 0x0342, 0x03c5, 0x0308,
0x0300, 0x03c5, 0x0308, 0x0301, 0x03c5, 0x0308, 0x0342, 0x03c9,
0x0342, 0x03b9, 0x0066, 0x0066, 0x0069, 0x0066, 0x0066, 0x006c};
#undef R
#undef S
static const struct {
const unsigned *map;
const unsigned *data;
size_t map_size;
unsigned n_codepoints;
} FOLD_MAP_LIST[] = {
{FOLD_MAP_1, FOLD_MAP_1_DATA, SIZEOF_ARRAY(FOLD_MAP_1), 1},
{FOLD_MAP_2, FOLD_MAP_2_DATA, SIZEOF_ARRAY(FOLD_MAP_2), 2},
{FOLD_MAP_3, FOLD_MAP_3_DATA, SIZEOF_ARRAY(FOLD_MAP_3), 3}};
int i;
/* Fast path for ASCII characters. */
if (codepoint <= 0x7f) {
info->codepoints[0] = codepoint;
if (ISUPPER_(codepoint))
info->codepoints[0] += 'a' - 'A';
info->n_codepoints = 1;
return;
}
/* Try to locate the codepoint in any of the maps. */
for (i = 0; i < (int)SIZEOF_ARRAY(FOLD_MAP_LIST); i++) {
int index;
index = md_unicode_bsearch__(codepoint, FOLD_MAP_LIST[i].map,
FOLD_MAP_LIST[i].map_size);
if (index >= 0) {
/* Found the mapping. */
unsigned n_codepoints = FOLD_MAP_LIST[i].n_codepoints;
const unsigned *map = FOLD_MAP_LIST[i].map;
const unsigned *codepoints =
FOLD_MAP_LIST[i].data + (index * n_codepoints);
memcpy(info->codepoints, codepoints,
sizeof(unsigned) * n_codepoints);
info->n_codepoints = n_codepoints;
if (FOLD_MAP_LIST[i].map[index] != codepoint) {
/* The found mapping maps whole range of codepoints,
* i.e. we have to offset info->codepoints[0] accordingly. */
if ((map[index] & 0x00ffffff) + 1 ==
codepoints[0]) {
/* Alternating type of the range. */
info->codepoints[0] =
codepoint +
((codepoint &
0x1) == (map[index] & 0x1)
? 1
: 0);
} else {
/* Range to range kind of mapping. */
info->codepoints[0] +=
(codepoint -
(map[index] & 0x00ffffff));
}
}
return;
}
}
/* No mapping found. Map the codepoint to itself. */
info->codepoints[0] = codepoint;
info->n_codepoints = 1;
}
#endif
#if defined MD4C_USE_UTF16
#define IS_UTF16_SURROGATE_HI(word) (((WORD)(word)&0xfc00) == 0xd800)
#define IS_UTF16_SURROGATE_LO(word) (((WORD)(word)&0xfc00) == 0xdc00)
#define UTF16_DECODE_SURROGATE(hi, lo) \
(0x10000 + \
((((unsigned)(hi)&0x3ff) << 10) | (((unsigned)(lo)&0x3ff) << 0)))
static unsigned md_decode_utf16le__(const CHAR *str, SZ str_size, SZ *p_size)
{
if (IS_UTF16_SURROGATE_HI(str[0])) {
if (1 < str_size && IS_UTF16_SURROGATE_LO(str[1])) {
if (p_size != NULL)
*p_size = 2;
return UTF16_DECODE_SURROGATE(str[0], str[1]);
}
}
if (p_size != NULL)
*p_size = 1;
return str[0];
}
static unsigned md_decode_utf16le_before__(MD_CTX *ctx, OFF off)
{
if (off > 2 && IS_UTF16_SURROGATE_HI(CH(off - 2)) &&
IS_UTF16_SURROGATE_LO(CH(off - 1)))
return UTF16_DECODE_SURROGATE(CH(off - 2), CH(off - 1));
return CH(off);
}
/* No whitespace uses surrogates, so no decoding needed here. */
#define ISUNICODEWHITESPACE_(codepoint) md_is_unicode_whitespace__(codepoint)
#define ISUNICODEWHITESPACE(off) md_is_unicode_whitespace__(CH(off))
#define ISUNICODEWHITESPACEBEFORE(off) md_is_unicode_whitespace__(CH((off)-1))
#define ISUNICODEPUNCT(off) \
md_is_unicode_punct__( \
md_decode_utf16le__(STR(off), ctx->size - (off), NULL))
#define ISUNICODEPUNCTBEFORE(off) \
md_is_unicode_punct__(md_decode_utf16le_before__(ctx, off))
static inline int md_decode_unicode(const CHAR *str, OFF off, SZ str_size,
SZ *p_char_size)
{
return md_decode_utf16le__(str + off, str_size - off, p_char_size);
}
#elif defined MD4C_USE_UTF8
#define IS_UTF8_LEAD1(byte) ((unsigned char)(byte) <= 0x7f)
#define IS_UTF8_LEAD2(byte) (((unsigned char)(byte)&0xe0) == 0xc0)
#define IS_UTF8_LEAD3(byte) (((unsigned char)(byte)&0xf0) == 0xe0)
#define IS_UTF8_LEAD4(byte) (((unsigned char)(byte)&0xf8) == 0xf0)
#define IS_UTF8_TAIL(byte) (((unsigned char)(byte)&0xc0) == 0x80)
static unsigned md_decode_utf8__(const CHAR *str, SZ str_size, SZ *p_size)
{
if (!IS_UTF8_LEAD1(str[0])) {
if (IS_UTF8_LEAD2(str[0])) {
if (1 < str_size && IS_UTF8_TAIL(str[1])) {
if (p_size != NULL)
*p_size = 2;
return (((unsigned int)str[0] & 0x1f) << 6) |
(((unsigned int)str[1] & 0x3f) << 0);
}
} else if (IS_UTF8_LEAD3(str[0])) {
if (2 < str_size && IS_UTF8_TAIL(str[1]) &&
IS_UTF8_TAIL(str[2])) {
if (p_size != NULL)
*p_size = 3;
return (((unsigned int)str[0] & 0x0f) << 12) |
(((unsigned int)str[1] & 0x3f) << 6) |
(((unsigned int)str[2] & 0x3f) << 0);
}
} else if (IS_UTF8_LEAD4(str[0])) {
if (3 < str_size && IS_UTF8_TAIL(str[1]) &&
IS_UTF8_TAIL(str[2]) && IS_UTF8_TAIL(str[3])) {
if (p_size != NULL)
*p_size = 4;
return (((unsigned int)str[0] & 0x07) << 18) |
(((unsigned int)str[1] & 0x3f) << 12) |
(((unsigned int)str[2] & 0x3f) << 6) |
(((unsigned int)str[3] & 0x3f) << 0);
}
}
}
if (p_size != NULL)
*p_size = 1;
return (unsigned)str[0];
}
static unsigned md_decode_utf8_before__(MD_CTX *ctx, OFF off)
{
if (!IS_UTF8_LEAD1(CH(off - 1))) {
if (off > 1 && IS_UTF8_LEAD2(CH(off - 2)) &&
IS_UTF8_TAIL(CH(off - 1)))
return (((unsigned int)CH(off - 2) & 0x1f) << 6) |
(((unsigned int)CH(off - 1) & 0x3f) << 0);
if (off > 2 && IS_UTF8_LEAD3(CH(off - 3)) &&
IS_UTF8_TAIL(CH(off - 2)) && IS_UTF8_TAIL(CH(off - 1)))
return (((unsigned int)CH(off - 3) & 0x0f) << 12) |
(((unsigned int)CH(off - 2) & 0x3f) << 6) |
(((unsigned int)CH(off - 1) & 0x3f) << 0);
if (off > 3 && IS_UTF8_LEAD4(CH(off - 4)) &&